{"id":"W3214379748","doi":"","title":"Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Training (meteorology); Computer science; Artificial intelligence; Machine learning; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02748295,0.0003935054,0.0005821779,0.0005732608,0.001591565,0.002568274,0.001621754,0.002145715,0.007078965],"category_scores_gemma":[0.2275413,0.0002969812,0.0002997686,0.0007234538,0.0044593,0.006182563,0.001781047,0.004347698,0.0006175652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002352862,"about_ca_system_score_gemma":0.001499127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004503473,"about_ca_topic_score_gemma":0.004266958,"domain_scores_codex":[0.9912853,0.006350435,0.0002819377,0.0007806874,0.0008578019,0.0004438079],"domain_scores_gemma":[0.7539429,0.2104252,0.01181929,0.0141318,0.006517386,0.003163382],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007895449,0.004993763,0.2757632,0.0007104882,0.0006315686,0.0004023632,0.007774654,0.08184268,0.004733455,0.335427,0.01963763,0.2601878],"study_design_scores_gemma":[0.001016362,0.002340492,0.125494,0.0003728157,0.0002215863,0.0002894363,0.005264857,0.3416406,0.004596226,0.5081711,0.01047295,0.0001195193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9622537,0.0006511427,0.01714801,0.006559093,0.00008512339,0.00009381629,0.0001309976,0.00006570716,0.01301235],"genre_scores_gemma":[0.9968568,0.00006935409,0.001560628,0.0002439648,0.00002355703,0.00003101079,0.0000526457,0.00002109608,0.001140913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9725171,"threshold_uncertainty_score":0.1453454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1161021505810194,"score_gpt":0.4009260998072039,"score_spread":0.2848239492261845,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}